"Analysis of calcium imaging data via finite nested mixture models"

Recent advancements in miniaturized fluorescence microscopy have made it possible to investigate neuronal responses to external stimuli in awake behaving animals through the analysis of intracellular calcium signals. We propose a nested Bayesian finite mixture specification that allows estimating the underlying spiking activity and, simultaneously, reconstructing the distributions of the calcium transient spikes' amplitudes under different experimental conditions. The proposed model leverages two nested layers of random discrete mixture priors to borrow information between experiments and discover similarities in the distributional patterns of neuronal responses to different stimuli. To provide theoretical support to the introduced formulation, we investigate the correlation structure and the partial EPPF of the proposed prior, and we compare it with other well-known nonparametric nested priors.

The link Teams is available here.